Sophomoresty GitHub avatar

gemini-search-mcp

Sophomoresty

An MCP server that lets AI agents perform free, unlimited web search via Google AI Mode (Gemini) without needing an API key.

Stars

163

7-day growth

No data

Forks

27

Open issues

0

License

No data

Last updated

2026-06-30

AI repository intelligence
FR-AI / ANALYSIS

Why it is worth attention

It offers a free, unlimited, high-quality web search alternative to paid services like Tavily or Grok MCP, leveraging Google's search index and Gemini synthesis, with easy integration into popular AI agents.

Who it is for

  • Developers using Claude, Cursor, Windsurf, or other MCP-compatible AI agents
  • Users who need real-time web search in AI workflows without paying per-query
  • Researchers and enthusiasts building AI tools that require current information
  • Anyone seeking to bypass API quotas and costs for web search functionality

Use cases

  • Adding real-time web search to Claude Desktop or Claude Code via MCP
  • Building AI agents that fetch current news, prices, or facts on demand
  • Replacing Tavily, SerpAPI, or Grok MCP with a free self-hosted alternative
  • Providing web search capabilities to custom applications through the OpenAI-compatible API

Strengths

  • Completely free and unlimited with no API key or quota, as stated in the README
  • Google-quality results via Gemini synthesis grounded in real-time search
  • Fast average response time of ~1.5 seconds per query
  • Works with multiple MCP clients (Claude, Cursor, Windsurf) and also offers an OpenAI-compatible endpoint

Considerations

  • Requires a local Chrome, Edge, or Chromium installation to function
  • No conversational memory between requests – each query is independent
  • Answer extraction relies on Google's DOM structure and may break if Google changes its layout
  • Streaming is chunked, not per-token, which may affect real-time applications

README quick start

Quick Start

Description

Free MCP server for web search powered by Google AI Mode (Gemini). Unlimited, no API key.

Related repositories

Similar projects matched by category, topics, and programming language.

lopopolo
Featured
lopopolo GitHub avatar

harness-engineering

Harness Engineering is a methodology for improving coding agent outputs by carefully crafting the environment around them—providing curated context, tools, and executable constraints that encode an organization’s nonfunctional requirements and cumulative lessons.

AI & Machine LearningAI Agents
2,390
slvDev
Featured
slvDev GitHub avatar

esp32-ai

A 28.9 million parameter language model runs on an $8 ESP32-S3 microcontroller entirely on-device, generating simple stories at about 9.5 tokens per second.

AI & Machine LearningLarge Language Models
1,960
littledivy
Featured
littledivy GitHub avatar

mimic

mimic captures traffic from any iOS or web app and automatically generates a Python client library that lets you call the app's API like a regular library.

AI & Machine Learning
1,482